Energy-Aware Multi-Server Mobile Edge Computing: A Deep Reinforcement Learning Approach

被引:0
|
作者
Naderializadeh, Navid [1 ]
Hashemi, Morteza [2 ]
机构
[1] Intel Corp, Mountain View, CA 92121 USA
[2] Univ Kansas, Lawrence, KS 66045 USA
关键词
Mobile edge computing; Deep reinforcement learning; Deep Q-networks; Multi-server offloading;
D O I
10.1109/ieeeconf44664.2019.9049050
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We investigate the problem of computation offloading in a mobile edge computing architecture, where multiple energy-constrained users compete to offload their computational tasks to multiple servers through a shared wireless medium. We propose a multi-agent deep reinforcement learning algorithm, where each server is equipped with an agent, observing the status of its associated users and selecting the best user for offloading at each step. We consider computation time (i.e., task completion time) and system lifetime as two key performance indicators, and we numerically demonstrate that our approach outperforms baseline algorithms in terms of the trade-off between computation time and system lifetime.
引用
收藏
页码:383 / 387
页数:5
相关论文
共 50 条
  • [1] An energy-aware Edge Server Placement Algorithm in Mobile Edge Computing
    Li, Yuanzhe
    Wang, Shangguang
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON EDGE COMPUTING (IEEE EDGE), 2018, : 66 - 73
  • [2] Deep Reinforcement Learning Empowers Wireless Powered Mobile Edge Computing: Towards Energy-Aware Online Offloading
    Jiao, Xianlong
    Wang, Yating
    Guo, Songtao
    Zhang, Hong
    Dai, Haipeng
    Li, Mingyan
    Zhou, Pengzhan
    [J]. IEEE TRANSACTIONS ON COMMUNICATIONS, 2023, 71 (09) : 5214 - 5227
  • [3] QoS-aware Mobile Edge Computing System: Multi-server Multi-user Scenario
    Kan, Te-Yi
    Chiang, Yao
    Wei, Hung-Yu
    [J]. 2018 IEEE GLOBECOM WORKSHOPS (GC WKSHPS), 2018,
  • [4] Deep Reinforcement Learning-Based Server Selection for Mobile Edge Computing
    Liu, Heting
    Cao, Guohong
    [J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2021, 70 (12) : 13351 - 13363
  • [5] A Deep Reinforcement Learning Approach for Collaborative Mobile Edge Computing
    Wu, Jiaqi
    Lin, Huang
    Liu, Huaize
    Gao, Lin
    [J]. IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022), 2022, : 601 - 606
  • [6] A Deep Reinforcement Learning Based Approach for Cost- and Energy-Aware Multi-Flow Mobile Data Offloading
    Zhang, Cheng
    Liu, Zhi
    Gu, Bo
    Yamori, Kyoko
    Tanaka, Yoshiaki
    [J]. IEICE TRANSACTIONS ON COMMUNICATIONS, 2018, E101B (07) : 1625 - 1634
  • [7] Dynamic and intelligent edge server placement based on deep reinforcement learning in mobile edge computing
    Jiang, Xiaohan
    Hou, Peng
    Zhu, Hongbin
    Li, Bo
    Wang, Zongshan
    Ding, Hongwei
    [J]. AD HOC NETWORKS, 2023, 145
  • [8] Energy-Aware Application Placement in Mobile Edge Computing: A Stochastic Optimization Approach
    Badri, Hossein
    Bahreini, Tayebeh
    Grosu, Daniel
    Yang, Kai
    [J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2020, 31 (04) : 909 - 922
  • [9] Risk-Aware Energy Scheduling for Edge Computing With Microgrid: A Multi-Agent Deep Reinforcement Learning Approach
    Munir, Md Shirajum
    Abedin, Sarder Fakhrul
    Tran, Nguyen H.
    Han, Zhu
    Huh, Eui-Nam
    Hong, Choong Seon
    [J]. IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2021, 18 (03): : 3476 - 3497
  • [10] SMCoEdge: Simultaneous Multi-server Offloading for Collaborative Mobile Edge Computing
    Xu, Changfu
    Li, Yupeng
    Chu, Xiaowen
    Zou, Haodong
    Jia, Weijia
    Wang, Tian
    [J]. ALGORITHMS AND ARCHITECTURES FOR PARALLEL PROCESSING, ICA3PP 2023, PT V, 2024, 14491 : 73 - 91